Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/hachej/boring-ui/boring-loop-implementnpx skills add hachej/boring-ui --skill boring-loop-implementgit clone --depth 1 https://github.com/hachej/boring-uiWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00047 | $0.00478 |
| Opus 5 | $0.00023 | $0.00239 |
| Sonnet 5 | $0.00009 | $0.00096 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
boring-loop-implement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Boring Loop Implement
Implement one issue or one approved plan slice.
Canonical model: ../../../../../docs/kanzen/boring-loop.md.
Coding rules: ../../../../../docs/kanzen/procedures/coding-rules.md.
Trunk/flag/review budget: ../../../../../docs/kanzen/procedures/trunk-flags-review-budget.md.
Visual review: ../../../../../docs/kanzen/procedures/visual-review.md.
Proof comments: ../../../../../docs/kanzen/procedures/proof-of-work.md.
Steps
- Read the issue, plan, acceptance, flag/abstraction path, proof requirement, related PRs, newest owner comments, and repo invariants.
- Use the smallest lane that works: local trunk when allowed, otherwise a short-lived branch/worktree.
- Code only the accepted slice. Keep production-code additions near the review budget or split before coding.
- Run focused checks and demo workspace proof when UI/workspace behavior changes.
- Open or update a PR that links the primary issue and names proof.
- Run review, fix every accepted finding, and re-review until clean or blocked. Use thermo-nuclear review for non-trivial code.
- Ensure proof, review, thermo, and CI match the current head SHA.
- Land the plane: prepare a review card with PR URL, issue URL, summary, proof, demo URL or waiver, known gaps, and exact owner decision needed.
Exit
- Not clear:
state:blocked phase:grill track:owner. - Needs plan/split:
state:active phase:plan track:owner. - Needs fixes/proof:
state:active phase:review track:owner. - Ready for owner:
state:ready phase:merge track:owner. - Fast-track only when every checklist item in
boring-loop.mdpasses.
Workers may use subagents for slices or review, but the parent lane owns the issue/PR and records the final state.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 43 lines · 47 tokens per session scan A ebc5a10e7c96
boring-loop-implement is a skill published in the GitHub repository hachej/boring-ui (46 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 478 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
prepare-paperclip-pr
Prepare a Paperclip branch for PR with commits, template body, and checks.
apm-issue-autopilot
Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…
dispatch
Use when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it"…
flow-next-work
Execute a flow-next spec or task end-to-end with worker subagents, gates, and commits. Use when asked to work on, implement, or execute fn-N.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.
cursor-agents-workflow
Human handoff, Linear branch names, reviewable (non-draft) PRs, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and review-doubt notes for Cursor agents. Use when a Cursor Cloud or Cursor desktop agent implements a Linear issue, opens a GitHub PR, asks a human to…